Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code snippets and data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ऑर्गेना
    0.43
    áció
    0.41
     averted
    0.38
    elaar
    0.37
    образной
    0.37
     भीड़
    0.36
     Siem
    0.35
     كده
    0.35
     karşı
    0.35
     Raum
    0.35
    POSITIVE LOGITS
     fistula
    0.39
    不用
    0.34
     ವ್ಯ
    0.34
    ็ง
    0.34
     gram
    0.33
     পত্র
    0.33
     flute
    0.33
     setSearch
    0.33
     dyslexia
    0.33
    ଵ
    0.33
    Act Density 0.010%

    No Known Activations